page       attach   
EXplainable and TRAnsparent AI and Multi-Agent Systems: Fourth International Workshop
Auckland, New Zealand, 09/05/2022–10/05/2022

The aim of the workshop is to gather researchers interested in developing an explainable agency for goal-oriented agents and robots supported by machine learning mechanisms. In particular, participants are invited to submit papers addressing whichever phase of explainability (e.g., generation, communication, and reception) fostering transparency in Autonomous Agents and Multi-Agent Systems (MAS) and robots. Compliance with such requirements is becoming necessary in most systems where agent-oriented approaches are increasingly employed. 

Therefore, the purpose of this fourth “International workshop on Explainable Intelligence in fourth Agent and Multi-Agent Systems” (EXTRAAMAS) is five-fold:
(i) to strengthen the common ground for the study and development of explainable and understandable autonomous agents, robots, and Multi-Agent Systems (MAS),
(ii) to explore how agent explainability and machine learning interpretability can be combined to achieve systems capable of both perceptual data-driven and cognitive goal-driven explainability
(iii) to investigate the potential of agent-based systems in for personalized user-aware explainable AI,
(iv) to assess the impact of transparent and explained solutions on the user/agents behaviors,
(v) to discuss motivating examples and concrete applications in which the lack of explainability leads to problems, which would be resolved by explainability,
(vi) to assess and discuss the first demonstrators and proof of concepts paving the way for the next generation systems,
(vii) to explore the emerging interactions and synergies between XAI and law 

topics of interest
  • Special Focus: XAI & Law
    • The legal requirements of explainability 
    • How does the (technical) human-in-the-loop approach relate to the (legal) notion of automated decision making? 
    • XAI application in the domain of law 
    • (X)AI for legal explanations 
    • (X)AI for explaining legal decisions 
  • Explainable Agents and Robots
    • Explainable agent architectures 
    • Personalized XAI 
    • Explainable & Expressive robots 
    • Explainable human-robot collaboration 
    • Reinforcement Learning Agents 
    • Multi-modal explanations 
  • XAI & Ethics
    • Social XAI 
    • AI, ethics, and explainability 
    • XAI vs AI 
  • XAI & MAS
    • Multi-actors interaction in XAI 
    • XAI for agent/robots teams 
    • Simulations for XAI 
  • Interdisciplinary Aspects
    • Cognitive and social sciences perspectives on explanations 
    • HCI for XAI 
    • Legal aspects of explainable agents 
    • Explanation visualization 
  • XAI Machine learning and Knowledge Representation
    • Bridging symbolic and subsymbolic XAI 
    • Knowledge generation from interpretations 
    • Explanation visualization 
    • Explainable knowledge generation 
hosting event
works as
origin event for publication
page_white_acrobatSemantic Web-based Interoperability for Intelligent Agents with PSyKE (paper in proceedings, 2022) — Federico Sabbatini, Giovanni Ciatto, Andrea Omicini
page_white_acrobatOn the Design of PSyKI: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors (paper in proceedings, 2022) — Matteo Magnini, Giovanni Ciatto, Andrea Omicini
hosting event for talk
page_white_powerpointOn the Design of PSyKI: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors (EXTRAAMAS 2022@AAMAS 2022, 09/05/2022) — Matteo Magnini (Matteo Magnini, Giovanni Ciatto, Andrea Omicini)
page_white_powerpointSemantic Web-based Interoperability for Intelligent Agents with PSyKE (EXTRAAMAS 2022@AAMAS 2022, 09/05/2022) — Federico Sabbatini (Federico Sabbatini, Giovanni Ciatto, Andrea Omicini)
hosted event for
series event